Which statistical test would I use

[Mary McIntosh]

If I want to find out if a treatment has an impact on the scores of an assement tool, how would I go about finding this out?  I have two time of assessment :  baseline and follow up.  I have five factors of the assessment tool and a total score on the assessment tool.

[Art Kendall]

A lot would depend on the meanings of the constructs represented by the 5 factors.

Are the factors derived from a well-established instrument?

Are the factors facets of a single construct?

How many respondents do you have?

Do you hypothesize that specific factors would change and not others?

What are the constructs represented by the 5 factors?

Do you have only the scores or do you have the items that are used to get the scores?

do you have a comparison group that did not receive the treatment?
Is that comparison group a control group? I.e., were treat vs comparison assigned at random?

On 5/11/2014 5:32 PM, Mary McIntosh [via SPSSX Discussion] wrote:

If I want to find out if a treatment has an impact on the scores of an assement tool, how would I go about finding this out?  I have two time of assessment :  baseline and follow up.  I have five factors of the assessment tool and a total score on the assessment tool.

---

If you reply to this email, your message will be added to the discussion below:

http://spssx-discussion.1045642.n5.nabble.com/Which-statistical-test-would-I-use-tp5725963.html

To start a new topic under SPSSX Discussion, email [hidden email]
To unsubscribe from SPSSX Discussion, click here.
NAML